Ling-3.0-tiny-GGUF
GGUF conversions of inclusionAI/Ling-3.0-tiny, converted directly from the released BF16 safetensors.
Params
—
Context
131,072
Downloads 30d
242 K
Likes
116
Download history
daily snapshots · 27 days265 K188 K
Sep 28Oct 7Oct 16Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Ling-3.0-tiny-IQ1_S.gguf | IQ1_S | 1.8 GB | 2.4 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ1_M.gguf | IQ1_M | 1.9 GB | 2.6 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ2_XXS.gguf | IQ2_XXS | 2.2 GB | 2.9 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ2_S.gguf | IQ2_S | 2.5 GB | 3.2 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ2_XS.gguf | IQ2_XS | 2.4 GB | 3.2 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ2_M.gguf | IQ2_M | 2.7 GB | 3.5 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-IQ3_S.gguf | IQ3_S | 3.5 GB | 4.4 GB | ✅ Runs comfortably |
| Ling-3.0-tiny-BF16.gguf | GGUF | 15.8 GB | 17.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run ling-3-0-tiny-gguf # pin the quantization explicitly $ ollama run ling-3-0-tiny-gguf-gguf
$ huggingface-cli download bloomer010/Ling-3.0-tiny-GGUF-GGUF \
Ling-3.0-tiny-BF16.gguf --local-dir .
$ llama-cli -m Ling-3.0-tiny-BF16.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/ling-3-0-tiny-gguf
{
"hf_id": "bloomer010/Ling-3.0-tiny-GGUF",
"params_b": null,
"context_length": 131072,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 241829,
"vram_estimates": [
{ "quant": "GGUF", "gb": 17.9 },
{ "quant": "IQ1_M", "gb": 2.6 }
],
"updated_at": "2026-09-28T01:00:30Z"
}
Specifications
- Architecture
- BailingMoeV3ForCausalLM
- Context length
- 131,072
- Vocabulary
- 157,184
- Layers / heads
- 24 / 16
- Licence
- mit
- First seen on the Hub
- 2026-08-11
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-28
Compare with any text-generation model